The Proof is in the Textual Pudding

Social media and online news have fundamentally changed the way people interact with companies. Posts on platforms like Twitter or LinkedIn, along with blogs and online news articles, provide accounts of stakeholder experiences with companies and their perception of corporate behaviour and allow for the rapid spread of these views. The latter shapes stakeholder perspectives and informs stakeholder actions. As such, social media and online news quickly mirrors and shapes corporate reputation, societal legitimacy, social license to operate, and stakeholder trust [1]. An illustrative example is H&M’s “trashgate” scandal, where store personnel were found to be damaging and dumping unsold clothes in the garbage instead of donating them. Starting with an article in the New York Times, public outrage quickly spread across social media [2]. It was one of the top-three trending topics on Twitter and remained so for several days. Only after the outrage, H&M decided to address the issue. After investigations, it was discovered that the particular New York store was violating the company’s policy which was to donate unsold clothing to charity. “Trashgate” was one of the first examples to show the ways in which social media could raise issues to news  coverage, affect corporate publicity, and force companies to change their actions [3]. It also illustrates how social monitoring can be a powerful asset in the world of sustainability, especially in terms of evaluating Environmental, Social and Governance (“ESG”) risk. 

Over recent years, the use of ESG data and analytics has boomed in capital markets [4]. Real-time news and social media data are receiving increasing attention in cutting-edge decision-making strategies. This popularity is grounded in the ability of ESG data to provide insights that are absent from typical financial data. Traditional financial information has limited usefulness to investors today as it allows for data that is both backwards-looking and that only encompasses a narrow financial base. As such, it is insufficient on its own to assess a company’s ability for future profit. For example, financial data did not indicate potential unethical behaviour by H&M, and it only picked up on the reputational (and financial) damage thereof once it had already happened. Therefore, both retail and institutional investors increasingly focus on ESG factors to assess companies. This is supported by ESG research that shows the positive relationship between a firm’s profitability and its ESG metrics [5] and illustrates that ESG data can help reduce portfolio risk [6]. 

However, ESG data in mainstream investing has three main challenges: most ESG data is qualitative, the landscape of corporate disclosures is incomplete and inconsistent, and disclosures are generally voluntary with sparse available data [7][8]. Many pertinent issues do not manifest in disclosures or regulatory filings and, if they do, the delays caused by reporting and publication cycles can cause relevant data to be out of date by the time it is in the public domain. There is also a significant bottleneck in assessing ESG performance due to the manual effort in continuously sourcing and validating disclosure data. This bottleneck is even more prominent when dealing with large volumes of unstructured text data, such as social media or news. As demand for ESG increases, the need for accurate and near real-time responses to ESG issues becomes clear, and the ability to detect and represent such issues through data sources beyond a company’s filings is paramount. In the ever-changing investment landscape, news and social media data utilisation have become critical to ESG investment strategies. 

To properly realise the potential of news data, millions of articles need to be processed daily, and one must look towards the power and capability of Machine Learning (“ML”). Latest advances in Natural Language Processing (“NLP”) increase/strengthen our ability to process unstructured text data. Moving away from pre-determined text/keyword ontologies of the past [9], advances in the field of deep learning have pushed the state-of-the-art towards Transformer-based architectures such as BERT [10]. The key advantage here is leveraging context in decision making. Language is complex – for example, homographs exist, words whose meaning is entirely dependent on context. Without contextual understanding, false positives are likely, and many prominent classical methods are known to fall into this trap. Such approaches have focused on words and the frequency of their occurrence, with words weighted by how often they appear. For example, if a corpus of articles frequently mentions the word ‘exploitation’, such techniques can systematically discount its relevance. Similarly, identifying the difference between the word ‘carbon’ in the context of greenhouse gas emissions or when discussing carbon allotropes is critical in understanding the text in question. In other words, “context is king”. 

Across the investment community, researchers and engineers are using machine learning in new and disruptive ways, analysing linguistic information from content, using ESG and sentiment data to determine a company’s commitment to ESG, and evaluating the impact of this commitment on stakeholders. [11] Sokolov et al. [12] show how BERT can be used as a classifier to aid in ESG Scoring, with aggregation approaches used on the output to construct a score. Such scores allow investors to recognise and understand what drives high and low ESG performance among their holdings, informing their approach for engagement. For instance, reflecting the impact of “trashgate” in their decision-making process for H&M. These also supplement brand and reputational risk management with a specific focus on sustainability issues and controversies.  

At Arabesque S-Ray, we are committed to providing innovative tools and incisive insight into ESG data to empower businesses and investors. This includes substantial focus on applied NLP research,  perfecting cutting-edge techniques and deepening sustainability expertise to provide granular insight into corporate behaviours. We are working to design the leading NLP-powered ESG-focused tools that will transform the way investors access and use social and traditional media signals in sustainable investing and aiding responsible business.   

References 

[1] – Pekka Aula, (2010),”Social media, reputation risk and ambient publicity management”, Strategy & Leadership, Vol. 38 Iss: 6 pp. 43 – 49 

[2] – ‘‘Reputational risk in digital publicity’’ presented at the Viestinna¨n tutkimuksen pa¨iva¨t, February 12th, 2010, Tampere, Helsinki. 

[3] – Laaksonen SM. Hybrid narratives: Organizational reputation in the hybrid media system. Publications of the Faculty of Social Sciences. 2017 Jun 16. 

[4] – Lev, B., & Zarowin, P. (1999). The boundaries of financial reporting and how to extend them. Journal of Accounting Research, 37(2), 353-385. 

[5] – Clark, Gordon L. and Feiner, Andreas and Viehs, Michael, From the Stockholder to the Stakeholder: How Sustainability Can Drive Financial Outperformance (March 5, 2015) 

[6] – Friede, G., T. Busch, and A. Bassen. 2015. “ESG and Financial Performance: Aggregated Evidence from More Than 2000 Empirical Studies.” Journal of Sustainable Finance & Investment 5 (4): 210–233 

[7] – Park, Andrew & Ravenel, Curtis. (2013). Integrating Sustainability Into Capital Markets: Bloomberg LP And ESG’s Quantitative Legitimacy. Journal of Applied Corporate Finance 

[8] – Henriksson, R., J. Livnat, P. Pfeifer, and M. Stump. 2019. “Integrating ESG in Portfolio Construction.” The Journal of Portfolio Management 45 (4): 67–81. 

[9] – Lee Y. H., W. J. Tsao, and T. H. Chu. “Use of Ontology to Support Concept-Based Text Categorization.” In Designing E-Business Systems. Markets, Services, and Networks, edited by C. Weinhardt, S. Luckner, and J. Stößer, 201-213. WEB 2008. Lecture Notes in Business Information Processing, vol 22. Berlin, Heidelberg: Springer. 2009. 

[10] – Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 

[11] – https://www.raconteur.net/finance/investing/how-machine-learning-is-helping-investors-find-esg-stocks/ 

[12] – Building Machine Learning Systems for Automated ESG Scoring, Alik Sokolov, Jonathan Mostovoy, Jack Ding, Luis Seco, The Journal of Impact and ESG Investing Jan 2021 

Why ESG Data is Changing

Producing reliable environmental, social, and governance (ESG) data has become paramount for companies in the last few years. With it, they can demonstrate how they are reducing their carbon footprint, protecting their social capital, or complying with the booming disclosure landscape. 

Reliable ESG data helps companies identify potential risks, manage resources, and remain compliant with regulation. But it can be much more than a backwards looking tool. The most ambitious companies that we work with at Arabesque are looking to transform ESG data into a competitive advantage, producing actionable business intelligence which will set them apart from their competitors. 

The biggest hurdle to this is perhaps the most obvious. How can I ensure that I have access to reliable ESG data? What does it look like, and how can I gather it? These are the sort of questions which have, until recently, puzzled business leaders. They’re also the questions that we are answering at Arabesque. 

Looking at the first frameworks to regulate ESG data disclosure is like looking at an early map of the first railways. A hodgepodge of private enterprises, many overlapping and intertwining, suffering from a lack of unification. Today, companies have a confusing mixture of compulsory and voluntary frameworks to report against. Even if they fulfil their obligations, most reporting companies do not disclose the same data in the same way. Some are simply unaware of their obligations. 

Cutting through all this noise is crucial. Investors, underwriters, regulators (not to mention companies themselves) stand to benefit enormously from a market and supply chain greased with the oil of reliable data. But it is impossible for the vast majority of organisations to confidently gather the information required under their own steam. 

This is why companies look to the likes of Arabesque to supply global markets with transparent, accessible and coherent ESG information; to help investors respond to customer values, enable corporates to meet a growing wave of disclosure requirements, and to provide the wider market with meaningful signals that enable an informed allocation of capital.  

Our team prioritises Artificial Intelligence to help achieve this. We gather a vast amount of data; from traditional, more structured data, to a wide range of alternative sources of information such as the press, social media, or NGO activity. AI allows us to make sense of this highly complex mix of disclosed information and short-term signals. It can rationalise thousands of competing and overlapping sustainability metrics into a high-quality picture of a company’s ESG credentials. 

As the volume of sustainability data increases – in the next eighteen months we will see a slew of new regulatory requirements – it will become increasingly important for investors to work confidently with AI to make truly sustainable investment decisions. 

Customisation is now the next stage of the journey. Being able to take a detailed look at the underlying information which companies disclose, and filter through the thousands of data points to reach the specific insight which a business requires is swiftly becoming not a ‘nice to have’, but a business necessity for organisations looking to balance consumer demand with maximising returns. Arabesque’s ‘Temperature Score is just one example of this. 

Sustainability data will only become more important in years to come. The onus is now on companies to ready themselves with the tools needed to be leaders in using it. 

Throwing the net-zero baby out with the bathwater?

In the months following last November’s COP summit, a welcome urgency has entered the conversation surrounding financial markets and their role in slowing climate change. But alongside this, a growing schism is emerging that pits clean, ‘green’, investible assets against dirty, ‘brown’, soon-to-be stranded ones. We must nip this facile outlook in the bud, or risk foregoing an opportunity to rapidly reduce emissions across a vast majority of the investible universe. 

To view the world’s companies as either green or brown is to throw the net-zero baby out with the bathwater. By fixating on the extremities of this spectrum, we disregard the trillions of dollars of resource that the companies in between could deploy towards not only reducing their impact on the planet, but in some cases actively mitigating climate change elsewhere in the economy. It is time we engaged in a more grown-up conversation about the practicalities of a successful climate transition. 

Remembering that the world’s 100 biggest companies are responsible for more than 70% of global emissions it is clear that, important as it is, we cannot rely on fuelling ‘pure green’ companies to do more good as the sole solution. It is also critical that we mobilise capital to help the rest to do less bad. 

This is not permissiveness, or a concession. The global race to prevent irreversible damage to our planet is formed of multiple heats. One of these sprints, characterised by initiatives like the EU Taxonomy, is to rapidly channel capital to companies that directly slow climate change through their operations. However, another is to help companies with the resource and means to reduce their own impacts on the planet do so too. 

Out of 30,000 of the world’s biggest listed companies, only 1% of their collective revenues are derived from pure green activities as defined by the EU Taxonomy in its current form, and 12% from brown. Putting aside the wider issue of the potential bubble this may point towards, these figures demonstrate that the world’s ‘pure green’ businesses do not yet have the capacity to deploy the volumes of capital currently invested elsewhere. There simply isn’t enough room on the green bandwagon for the number of investors clamouring to get on board. 

So how can we put the remaining 87% of economic activity to good use? If we are to truly engage with those companies that are neither green nor brown, then markets need confidence that the transition is underway for them. Data and technology can and already do tell us this. 

Data show us that since the Paris Accord was signed in 2015, the share of companies in the FTSE 100 whose environmental impact is aligned to a 1.5C temperature rise limit rose from 57% to 66%. Among the S&P 500, that figure grew from 28% to 46%. With the UN’s climate panel warning that emissions must fall by half by 2030, these improvements are clearly not enough, but it is a signal that with the correct data and a market focus on these transition companies, net emission volumes among the world’s biggest companies will continue to fall. 

There are promising signs that this transition is gaining momentum. The volume of companies disclosing the sustainability data that enable markets to gauge their progress is growing. There are glimmers of harmonisation at the regulatory level, with disclosure frameworks like the TCFD being adopted by more countries. At a technical level, the International Financial Reporting Standards foundation, whose accounting standards are used by most of the world, is developing a framework for simple and consistent sustainability reporting. 

With these initiatives falling into place, the infrastructure will be there for financial markets to play their part in mitigating the climate crisis and meeting the many heady goals and ambitions set out in at COP. But to do this, we must recognise that whether we like it or not, we need more than a few companies being perfectly sustainable: we also need millions doing it imperfectly. 

At The Crossroads

“At The Crossroads – Leadership in the Age of Climate Change“ by Jouni Keronen and Mari Pantsar is a very timely book that offers a deep dive into the history and the causes of climate change and the available options to combat it at this late hour. The two Finish authors bring their lifelong experiences to bear, both as thinkers and as practitioners. In clear and simple language, they succeed in weaving together a compelling and solid narrative as they unpack and explain the scientific, historical, technological, economic and social aspects of manmade climate change.  

A central element of the book is that humans, who depend on a somewhat stable climate for their survival, health, safety and progress, have in recent decades become a geophysical force. We have overstepped natural boundaries by dumping billions of emissions into the atmosphere. Our wasteful lifestyles poison soil and water and destroy natural habitats, causing climate disasters and destruction of the natural environment.  

The authors pointedly probe the question what kind and what size of climate-related disasters will have to occur before the massive change efforts that are required to avoid the worst outcomes will be mobilized. Solutions for decarbonizing critical economic sectors are available. Environmental threats such as ozone depletion, urban pollution and acid rain have successfully been dealt with in the past. Effective carbon carbon pricing in particular would greatly accelerate the many efforts already under way. 

The authors explain why policy makers and societies have failed so far and lay out the case for immediate systemic and massive actions. As the latest IPCC report has shown, the window of opportunity to avert dangerous warming is closing. We are at a crossroads and our actions today will decide about humanity’s future. There are three possible future scenarios, depending on the actions we take now: 

The worst case is a hot house earth with much human suffering and chaos if we continue to postpone massive actions; a healthy and prosperous future can be achieved if we immediately start to employ systemic solutions such as effective carbon pricing; lastly, carrying forward incremental changes only will lead to a disorderly transition where governments eventually will be forced to take bold actions – the “ ban economy”. 

“At The Crossroads”, which is available free of charge, has great educational value. It is to be hoped that policymakers, business leaders, educators and laypeople will read it and absorb its message, as climate leadership has to be everybody’s concern. 

The book also provokes reflections. Here are my two cents’ worth:  

  1. My own generation, the baby boomers, have failed. We saw the writing on the wall but we did not take sufficient action. We found it convenient to ignore or postpone changes. We have built an enormous liability for our children and it is now our duty to correct our mistakes and to change course at the personal level and through the influence we still have. 
  1. Business and investors have at last started to take climate threats seriously. Decarbonization and circular material flows are becoming strategic guideposts for market success. But it is near-term action rather than long-term goal setting that needs to move center stage now. Decarbonizing the assets that were created in the past is one challenge. Moving ahead, however, we also need to ensure that we no longer build or maintain liabilities for the future, but instead mobilize investments that lead us to a carbon-neutral economy.  
  1. Policymakers need to wake up and understand the costs of inaction. Pretending that we can subsidize our way into the future without changing values and valuations will not work. It is time to be honest and to explain why systemic solutions – especially effective carbon pricing – are needed, to change the framework conditions in favor of decarbonization. Policymakers should not be allowed to hide behind cowardly and cynical arguments, such as that more ambitious actions would disadvantage the poorer segments of society. The opposite is true. The poor will suffer most from climate impacts. It is irresponsible not to protect society and the poor in particular. Moreover, the richest segments of societies have the biggest environmental footprint. If social concerns were truly the reason for postponing climate action, then clearly these concerns could easily be addressed as part of the transformation agenda.  
  1. Humanity as a whole needs to re-establish a healthy relationship with the natural environment. We all have a role to play and we all can make a contribution through our behavior. The choices we make on an individual level – how we travel, what we consume and how we invest – will be critical to change values and valuations. The book drives this message home. 
  1. We need to rediscover international cooperation. The United Nations itself can only do what big powers allow it to do. Paris was a success because of smart French diplomacy, European Union advocacy and, above all, the willingness by China and the United States to cooperate through the United Nations. The European Union has recently made great strides in laying the foundations for tackling the climate challenge through its expansion of the Emissions Trading System (ETS) and the willingness to link it with trade. Winning over other major powers to join a climate club that sets a minimum carbon price and phases out destructive subsidies for fossil fuels is one way to go. But rich countries have depleted most of the available carbon budget and therefore also have a responsibility to support developing countries in this transition. The promise made in Paris to provide climate finance to developing countries needs to be honored and more needs to be done. And maybe, just maybe, one day – hopefully soon – outdated foreign policy and power concepts will give way to planetary stewardship and climate politics based on the simple recognition that humanity has only one planet and that the real enemy is us.  

Temperature Score

Less than a quarter of the world’s biggest companies are on course to limit global temperature rise to 1.5 degrees Celsius by 2050, according to new analysis by Arabesque, a leading provider of technology solutions for sustainable finance.

Arabesque assessed fourteen of the world’s largest stock indexes between 2015 and 2019 using its TemperatureTM Score technology, including the FTSE 100, S&P 100, DAX and Nikkei. It found that just under 25% (24.84%) of companies listed on all the indexes are aligned with meeting the 1.5 degree goal, a key focus of COP26 and this week’s Leaders Summit on Climate.

Overall, European companies lead the way towards the 1.5 degrees Celsius target in 2050, with companies in the Stockholm 30 (50%), DAX 30 (39.29%), Helsinki 25 (33.33%) and SMI 20 (33.33%) the best performers. However, fewer than one in four companies in the FTSE 100 (23.08%) and S&P 100 (23.08%) are on course to meet the target, whilst only 8.51% of companies in the Hang Seng Index 55 and just 4.55% of those in Australia’s ASX 50 are aligned with the 1.5 degree goal. In Japan, 26.67% of companies in the Nikkei 225 are on course.

Arabesque’s data also shows that 15% of companies listed across the fourteen indexes are not publicly disclosing their greenhouse gas emissions, equating to approximately USD 5 trillion in market capitalisation. The Hang Seng Index has the highest number of non-disclosures, with 29% in 2019, compared to the FTSE 100 with the lowest at 2%.

Temperature ScoreTemperature ScoreTemperature Score

Dr. Rebecca Thomas, who led Arabesque’s research, said: “Over recent years, the quantity of corporate emissions data has increased significantly. Previous research from the Temperature Score shows that from 2014 to 2019, the proportion of companies disclosing at least scope 1 and scope 2 emissions rose by almost 25%. However, it is clear from our latest analysis that this has yet to translate into corporate climate action at scale. While overall progress is encouraging, a lot more needs to be done to keep the 1.5-degree goal within reach.”

Arabesque’s Temperature Score assesses thousands of data points to assign companies globally with a score in degrees Celsius to reflect their expected environmental impact by 2030 and 2050. Based on the new analysis of global indexes, it found that on average 70% of companies worldwide would satisfy the 2030 climate target of 2 degrees Celsius set out under the Paris Agreement, with 61% on track to meet the same goal by 2050, up from 41% in 2015 when the targets were adopted by 196 countries at COP 21. In recent years, however, scientists have underscored the need to limit planetary warming to 1.5 degrees Celsius in order to stave off the worst impacts of the climate crisis, an ambition that over 75% of companies analysed in Arabesque’s latest research are not currently on course to achieve.

Georg Kell, Chairman of Arabesque, added: “The array of public declarations and pledges ahead of COP 26 in Glasgow signifies a promising new alignment of ambitions to face the climate crisis. However, declarations of good intention by themselves are not going to lead to the required timely actions. In fact, despite the growing number of commitments, average carbon dioxide levels in the atmosphere have increased since 2015. This year is a potential turning point, offering corporate leaders a chance to think big and to act accordingly. But time is running out.”

Learn more about ESG Book products